Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full load. It helpfully enumerates what is returned (downloads, latest version, last-update date, release count), which is real behavioral detail, but says nothing about auth needs, rate limits, or what happens when the id is not found.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, zero filler. The lookup mechanics and return fields come first, then the decision context, which is the right front-loading for this tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description correctly enumerates the return fields, and the single required parameter is fully covered by the schema. The only gap is failure behavior for a bad or unknown id, which an agent would likely want to know.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the schema already carries an example ('dataview'), so the baseline is 3. The description adds the meaningful constraint that the id must be the exact directory id, distinguishing this from a fuzzy search input.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('look up one plugin by exact id') and scopes it to a single entry, which implicitly separates it from the search/browse siblings. An agent can tell this is a by-id lookup rather than a listing.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says when to use it: to judge whether a plugin is alive or abandoned before deciding to build, fork, or contribute. It does not name search_plugins or top_plugins as alternatives for the discovery case, so the routing guidance is good but not exhaustive.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full behavioral burden and does substantial work: it discloses the result shape (total match count plus top results), the ranking rule (sorted by downloads), and even an interpretation hint that an old last-update date 'means possibly abandoned.' It says nothing about rate limits, failures, or that the operation is a safe read, but for a public directory search the disclosure is above average.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, zero filler, and the most important routing instruction ('use this BEFORE building') is front-loaded right after the scope statement. Dense but every clause adds an actionable fact.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, and the description compensates by describing return contents, ranking, and how to interpret recency. Combined with the fully documented 2-parameter schema, an agent has everything needed to invoke and interpret the call correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, and the description goes beyond it by naming exactly which fields the keyword matches (name, id, author, description) and noting results are download-sorted. The 'limit' parameter is left to the schema, which documents it adequately.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource with scope: 'Search the official Obsidian community plugin directory (~9000 plugins) by keyword over name, id, author, and description.' The verb 'search' plus the directory scope makes it easy to separate from get_plugin (fetch one) and top_plugins (ranking list), though it never names those siblings explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear triggering conditions: 'Use this BEFORE building or proposing any Obsidian plugin or feature, to check whether it already exists, and whenever someone asks which plugin to use.' This is strong proactive guidance, but there is no when-not condition and no explicit routing to top_plugins or get_plugin for adjacent needs.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden, and it does disclose the return payload (total match count, repo links, supported dark/light modes, screenshot URLs) plus the case-insensitive all-keywords match behavior. It omits anything about pagination interaction with the limit cap, rate limits, or whether the directory lookup is unauthenticated, which keeps it out of 5 territory.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, no filler: purpose and scope first, usage trigger second, return shape third. Every sentence earns its place and nothing is repeated from the schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description must describe the return values — and it does, covering match count, repo links, supported modes, and screenshots. Combined with 100%-documented parameters, an agent has everything needed to call this correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents query, mode, and limit fully; the baseline is 3. The description reinforces query semantics (keyword over name and author) and the dark/light mode values, but adds no syntax or matching detail beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (Search), resource (official Obsidian community theme directory), scale (~900 themes), and the fields searched (name and author). The theme-vs-plugin distinction separates it cleanly from the search_plugins/top_plugins/get_plugin siblings without needing to name them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

"Use this before designing a new theme, or to recommend one" gives concrete triggering contexts rather than leaving usage implied. It stops short of naming alternatives or stating exclusions (e.g., when to prefer the plugin-directory siblings), so it is clear context but not full routing guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so the description carries the full burden. It usefully discloses the ordering semantics (descending by downloads), which the schema does not state, but omits return shape, pagination, the 100-item cap, and the empty-query behavior. Read-only intent is implied but never affirmed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two compact sentences, front-loaded with the action and scope, then the use case. No filler, no redundant restatement of the title.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple two-param, zero-required list tool with no output schema and no annotations, the description covers what the tool returns at a conceptual level (a ranked plugin list) and its optional filter. The main gap is silence on limit behavior and result ordering guarantees, which is minor at this complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 50%: 'query' is documented in the schema while 'limit' has no description there. The description restates the keyword filter ('optionally filtered by keyword') but says nothing about 'limit', its default of 25, or its maximum of 100, so it only partially compensates.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('List') and resource ('most-downloaded community plugins') with the ranking criterion folded into the resource itself, which separates it semantically from search_plugins. It does not explicitly name a sibling, but 'most-downloaded' is a clear distinguishing scope.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives a use case ('see which plugins dominate a category before entering it'), which implies a browse-first, discovery-oriented context. It never names search_plugins or get_plugin as alternatives, so the agent must infer when ranked listing beats keyword search.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.